openai-whisper-api

Name: openai-whisper-api
Availability: InStock
Author: lehalpaul

Transcribe audio files to text using the OpenAI Whisper API via cURL.

Updated Feb 4, 2026

Search Tags:#api #transcription #whisper #audio #openai #speech-to-text

Ready to run

npx skills add https://github.com/lehalpaul/agents --skill openai-whisper-api-lehalpaul

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: openai-whisper-api
Source: https://github.com/lehalpaul/agents/tree/main/skills/openai-whisper-api
Command: npx skills add https://github.com/lehalpaul/agents --skill openai-whisper-api-lehalpaul

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires curl, and includes scripts (resource) components.

What problem does it solve?

This Skill automates the transcription of audio files into text, making spoken content searchable and processable.

Core Features & Use Cases

Audio Transcription: Converts audio files (e.g., M4A, OGG) into text using OpenAI's Whisper API.
Customization: Allows specifying the model, output file path, language, and providing prompts for better accuracy.
Use Case: Transcribe a meeting recording to generate a text summary or convert voice notes into written text for easier editing and sharing.

Quick Start

Use the openai-whisper-api skill to transcribe the audio file '/path/to/audio.m4a'.

Frequently Asked Questions about openai-whisper-api

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I transcribe an audio file to text using the Whisper API?▼

You can transcribe audio files to text by submitting them to the OpenAI Whisper API via cURL. This process converts formats like M4A or OGG into written text while allowing you to customize parameters such as the model, language, and output format.

Do I need an OpenAI API key to convert speech to text?▼

Yes, converting speech to text with this method requires a valid OpenAI API key and the cURL binary installed. You must provide this API key in your cURL request to authenticate and process the audio transcription.

Can I customize the transcription parameters when converting audio files?▼

Yes, you can customize transcription parameters when converting audio files. The API allows you to specify the model, output file path, target language, and provide prompts to improve accuracy for specific spoken content.

What audio formats are supported for speech-to-text conversion?▼

The speech-to-text conversion supports various audio formats, including M4A and OGG. You can submit these files directly through cURL to the API to generate text transcripts of your voice notes or meeting recordings.

What is the best way to automate transcribing meeting recordings?▼

The best way to automate transcribing meeting recordings is using a script that sends audio files to the Whisper API via cURL. This approach quickly converts spoken content into text, making it searchable and ready for summary generation.

Are there limitations when using cURL for audio transcription?▼

A limitation of using cURL for audio transcription is the strict dependency on having the cURL binary installed and a valid OpenAI API key. Without these environment prerequisites, the automated transcription script cannot execute successfully.